Causal Reinforcement Learning

Causal reinforcement learning (CRL) aims to improve the efficiency and robustness of reinforcement learning (RL) agents by explicitly incorporating causal relationships into the learning process. Current research focuses on developing algorithms that can discover and utilize causal structures within the environment, often employing techniques like causal discovery, counterfactual reasoning, and structural causal models, to improve policy learning, state representation, and generalization. This approach promises to enhance the interpretability and reliability of RL agents, leading to more efficient learning and better performance in complex, real-world applications across diverse fields like robotics, healthcare, and wireless communication.

Papers

September 20, 2024

Causal Reinforcement Learning for Optimisation of Robot Dynamics in Unknown Environments
Julian Gerald Dcruz, Sam Mahoney, Jia Yun Chua, Adoundeth Soukhabandith, John Mugabe, Weisi Guo, Miguel Arana-Catania
Reinforcement Learning Causal Discovery Unknown Environment Optimization Process Robot Dynamic Autonomous Operation Causal Reinforcement Learning

September 7, 2024

Causality-Driven Reinforcement Learning for Joint Communication and Sensing
Anik Roy, Serene Banerjee, Jishnu Sadasivan, Arnab Sarkar, Soumyajit Dey
Reinforcement Learning Action Space Human Sensing Causal Reinforcement Learning Joint Task

August 24, 2024

Rethinking State Disentanglement in Causal Reinforcement Learning
Haiyao Cao, Zhen Zhang, Panpan Cai, Yuhang Liu, Jinan Zou, Ehsan Abbasnejad, Biwei Huang, Mingming Gong, Anton van den Hengel, Javen Qinfeng Shi
Reinforcement Learning Markov Decision Process Causal Reinforcement Learning

June 3, 2024

Causal prompting model-based offline reinforcement learning
Xuehui Yu, Yi Guan, Rujia Shen, Xin Li, Chen Tang, Jingchi Jiang
Causal Event Model Based Offline Reinforcement Learning Structured Prompting Causal Reinforcement Learning

May 11, 2024

Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals
Xiangwei Chen, Ruliang Xiaoa, Zhixia Zeng, Zhipeng Qiu, Shi Zhang, Xin Du
Reinforcement Learning Anomaly Detection Causal Inference Practical Method Human Sensing Semi Supervised Anomaly Detection Causal Reinforcement Learning

May 6, 2024

Out-of-Distribution Adaptation in Offline RL: Counterfactual Reasoning via Causal Normalizing Flows
Minjae Cho, Jonathan P. How, Chuangchuang Sun
Offline Reinforcement Learning Policy Learning Counterfactual Reasoning Offline Policy Evaluation Causal Reinforcement Learning Graph Out of Distribution Adaptation Graphical Normalizing Flow

February 7, 2024

Learning by Doing: An Online Causal Reinforcement Learning Framework with Causal-Aware Policy
Ruichu Cai, Siyang Huang, Jie Qiao, Wei Chen, Yan Zeng, Keli Zhang, Fuchun Sun, Yang Yu, Zhifeng Hao
LeArning Abstract Causal Structure Causal Structure Learning Causal Graphical Model Causal Reinforcement Learning

January 31, 2024

Causal Coordinated Concurrent Reinforcement Learning
Tim Tse, Isaac Chan, Zhitang Chen
Reinforcement Learning Sparse Reward Causal Reinforcement Learning

July 4, 2023

Causal Reinforcement Learning: A Survey
Zhihong Deng, Jing Jiang, Guodong Long, Chengqi Zhang
Reinforcement Learning Timely Survey Causal Reinforcement Learning

May 4, 2023

Causal Policy Gradient for Whole-Body Mobile Manipulation
Jiaheng Hu, Peter Stone, Roberto Martín-Martín
Action Space Causal Reinforcement Learning

February 26, 2023

Q-Cogni: An Integrated Causal Reinforcement Learning Framework
Cris Cunha, Wei Liu, Tim French, Ajmal Mian
Reinforcement Learning State of the Art Reinforcement Structural Causal Causal Reinforcement Learning

February 10, 2023

A Survey on Causal Reinforcement Learning
Yan Zeng, Ruichu Cai, Fuchun Sun, Libo Huang, Zhifeng Hao
Reinforcement Learning Timely Survey Markov Decision Process Causal Reinforcement Learning Multi Arm Bandit

November 28, 2022

Causal Deep Reinforcement Learning Using Observational Data
Wenxuan Zhu, Chao Yu, Qiang Zhang
Deep Reinforcement Learning Causal Inference Deep Q Learning Observational Data Model Free Deep Reinforcement Learning Unobserved Variable Causal Reinforcement Learning

November 2, 2022

Causal Counterfactuals for Improving the Robustness of Reinforcement Learning
Tom He, Jasmina Gajcin, Ivana Dusparic
Reinforcement Learning Native Robustness Causal Reinforcement Learning Invariant Causal

July 19, 2022

Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
Wenhao Ding, Haohong Lin, Bo Li, Ding Zhao
Reinforcement Learning Causal Discovery Causal Graph Goal Conditioned Reinforcement Learning Causal Reinforcement Learning Variational Causal

June 30, 2022

Causal Machine Learning: A Survey and Open Problems
Jean Kaddour, Aengus Lynch, Qi Liu, Matt J. Kusner, Ricardo Silva
Timely Survey Open Problem Causal Machine Learning Causal Explanation Causal Machine Causal Reinforcement Learning Causal Generative